Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- ljvmiranda921/tlunified-ner
|
| 5 |
+
language:
|
| 6 |
+
- tl
|
| 7 |
+
metrics:
|
| 8 |
+
- f1
|
| 9 |
+
library_name: spacy
|
| 10 |
+
pipeline_tag: token-classification
|
| 11 |
+
model-index:
|
| 12 |
+
- name: tl_gliner_small
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
type: token-classification
|
| 16 |
+
name: Named Entity Recognition
|
| 17 |
+
dataset:
|
| 18 |
+
type: tlunified-ner
|
| 19 |
+
name: TLUnified-NER
|
| 20 |
+
split: test
|
| 21 |
+
revision: 3f7dab9d232414ec6204f8d6934b9a35f90a254f
|
| 22 |
+
metrics:
|
| 23 |
+
- type: f1
|
| 24 |
+
value: 0.8540
|
| 25 |
+
name: F1
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
# GLiNER (medium) model finetuned on Tagalog data
|
| 29 |
+
|
| 30 |
+
This model was finetuned using the [GLiNER v2.5 suite](https://github.com/urchade/GLiNER) of models.
|
| 31 |
+
You can find and replicate the training pipeline on [Github](https://github.com/ljvmiranda921/calamanCy/tree/master/models/v0.1.0-gliner).
|
| 32 |
+
|
| 33 |
+
## Citation
|
| 34 |
+
|
| 35 |
+
Please cite the following papers when using these models:
|
| 36 |
+
|
| 37 |
+
```
|
| 38 |
+
@misc{zaratiana2023gliner,
|
| 39 |
+
title={GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer},
|
| 40 |
+
author={Urchade Zaratiana and Nadi Tomeh and Pierre Holat and Thierry Charnois},
|
| 41 |
+
year={2023},
|
| 42 |
+
eprint={2311.08526},
|
| 43 |
+
archivePrefix={arXiv},
|
| 44 |
+
primaryClass={cs.CL}
|
| 45 |
+
}
|
| 46 |
+
```
|
| 47 |
+
|
| 48 |
+
```
|
| 49 |
+
@inproceedings{miranda-2023-calamancy,
|
| 50 |
+
title = "calaman{C}y: A {T}agalog Natural Language Processing Toolkit",
|
| 51 |
+
author = "Miranda, Lester James",
|
| 52 |
+
booktitle = "Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)",
|
| 53 |
+
month = dec,
|
| 54 |
+
year = "2023",
|
| 55 |
+
address = "Singapore, Singapore",
|
| 56 |
+
publisher = "Empirical Methods in Natural Language Processing",
|
| 57 |
+
url = "https://aclanthology.org/2023.nlposs-1.1",
|
| 58 |
+
pages = "1--7",
|
| 59 |
+
}
|
| 60 |
+
```
|
| 61 |
+
|
| 62 |
+
If you're using the NER dataset:
|
| 63 |
+
|
| 64 |
+
```
|
| 65 |
+
@inproceedings{miranda-2023-developing,
|
| 66 |
+
title = "Developing a Named Entity Recognition Dataset for {T}agalog",
|
| 67 |
+
author = "Miranda, Lester James",
|
| 68 |
+
booktitle = "Proceedings of the First Workshop in South East Asian Language Processing",
|
| 69 |
+
month = nov,
|
| 70 |
+
year = "2023",
|
| 71 |
+
address = "Nusa Dua, Bali, Indonesia",
|
| 72 |
+
publisher = "Association for Computational Linguistics",
|
| 73 |
+
url = "https://aclanthology.org/2023.sealp-1.2",
|
| 74 |
+
doi = "10.18653/v1/2023.sealp-1.2",
|
| 75 |
+
pages = "13--20",
|
| 76 |
+
}
|
| 77 |
+
```
|